From ddbd669dc1f776d1a2f51384acd8cba8b453322a Mon Sep 17 00:00:00 2001
From: Peter Silva <peter@bsqt.homeip.net>
Date: Wed, 26 Jul 2023 23:14:15 -0400
Subject: [PATCH] issue #721 make magic an extra, degrade gracefully when
 missing. Also added *all* extra to install all extras.

---
 sarracenia/__init__.py      | 20 ++++++++++++++------
 sarracenia/flow/__init__.py |  9 ++++++---
 setup.py                    |  6 +++++-
 3 files changed, 25 insertions(+), 10 deletions(-)

diff --git a/sarracenia/__init__.py b/sarracenia/__init__.py
index 14e3337dd..f8392678a 100755
--- a/sarracenia/__init__.py
+++ b/sarracenia/__init__.py
@@ -31,7 +31,6 @@
 import datetime
 import importlib.util
 import logging
-import magic
 import os
 import os.path
 import paramiko
@@ -475,11 +474,15 @@ def fromFileData(path, o, lstat=None):
         if lstat :
             if os_stat.S_ISREG(lstat.st_mode):
                 m.__computeIdentity(path, o)
-                try:
-                    t = magic.from_file(path,mime=True)
-                    m['contentType'] = t
-                except Exception as ex:
-                    logging.info("trying to determine mime-type. Exception details:", exc_info=True)
+                if extras['filetypes']['present']:
+                    try:
+                        t = magic.from_file(path,mime=True)
+                        m['contentType'] = t
+                    except Exception as ex:
+                        logging.info("trying to determine mime-type. Exception details:", exc_info=True)
+                #else:
+                #    m['contentType'] = 'application/octet-stream' # https://www.rfc-editor.org/rfc/rfc2046.txt (default when clueless)
+                # I think setting a bad value is worse than none, so just omitting.
             elif os_stat.S_ISDIR(lstat.st_mode):
                 m['contentType'] = 'text/directory' # source: https://www.w3.org/2002/12/cal/rfc2425.html
             elif os_stat.S_ISLNK(lstat.st_mode):
@@ -804,6 +807,7 @@ def getContent(msg):
   
   amqp - ability to communicate with AMQP (rabbitmq) brokers
   mqtt - ability to communicate with MQTT brokers
+  filetypes - ability to
   ftppoll - ability to poll FTP servers
   vip  - enable vip (Virtual IP) settings to implement singleton processing
          for high availability support.
@@ -816,6 +820,7 @@ def getContent(msg):
    'ftppoll' : { 'modules_needed': ['dateparser', 'pytz'], 'present': False, 'lament' : 'will not be able to poll with ftp' },
    'humanize' : { 'modules_needed': ['humanize' ], 'present': False, 'lament': 'humans will have to read larger, uglier numbers' },
    'mqtt' : { 'modules_needed': ['paho.mqtt.client'], 'present': False, 'lament': 'will not be able to connect to mqtt brokers' },
+   'filetypes' : { 'modules_needed': ['magic'], 'present': False, 'lament': 'will not be able to set content headers' },
    'vip'  : { 'modules_needed': ['netifaces'] , 'present': False, 'lament': 'will not be able to use the vip option for high availability clustering' },
    'watch'  : { 'modules_needed': ['watchdog'] , 'present': False, 'lament': 'cannot watch directories' }
 }
@@ -837,6 +842,9 @@ def getContent(msg):
 
 # Some sort of graceful fallback, or good messaging for when dependencies are missing.
 
+if extras['filetypes']['present']:
+   import magic
+
 if extras['mqtt']['present']:
    import paho.mqtt.client
    if not hasattr( paho.mqtt.client, 'MQTTv5' ):
diff --git a/sarracenia/flow/__init__.py b/sarracenia/flow/__init__.py
index f3acbdc76..61f406ca8 100644
--- a/sarracenia/flow/__init__.py
+++ b/sarracenia/flow/__init__.py
@@ -1,7 +1,6 @@
 import copy
 import importlib
 import logging
-import magic
 import os
 import re
 
@@ -58,6 +57,9 @@
     'vip': None
 }
 
+if sarracenia.extras['filetypes']['present']:
+    import magic
+
 if sarracenia.extras['vip']['present']:
     import netifaces
 
@@ -1868,7 +1870,7 @@ def download(self, msg, options) -> bool:
                 os.rename(new_inflight_path, new_file)
             
             # older versions don't include the contentType, so patch it here.
-            if 'contentType' not in msg:
+            if sarracenia.extras['filetypes']['present'] and 'contentType' not in msg:
                 msg['contentType'] = magic.from_file(new_file,mime=True)
 
             self.metrics['flow']['transferRxBytes'] += len_written
@@ -1957,7 +1959,8 @@ def send(self, msg, options):
             local_path = '/' + msg['relPath']
 
         # older versions don't include the contentType, so patch it here.
-        if 'contentType' not in msg and not 'fileOp' in msg:
+        if sarracenia.extras['filetypes']['present'] and \
+           ('contentType' not in msg) and (not 'fileOp' in msg):
             msg['contentType'] = magic.from_file(local_path,mime=True)
 
         local_dir = os.path.dirname(local_path).replace('\\', '/')
diff --git a/setup.py b/setup.py
index 10908b46c..0ac91eb82 100755
--- a/setup.py
+++ b/setup.py
@@ -83,13 +83,17 @@ def read(*parts):
         'Topic :: System :: Logging',
     ],
     install_requires=[
-        "appdirs", "humanfriendly", "humanize", "jsonpickle", "python-magic", "paramiko",
+        "appdirs", "humanfriendly", "humanize", "jsonpickle", "paramiko",
         "psutil>=5.3.0", "watchdog"
     ],
     extras_require = {
        'amqp' : [ "amqp" ],
+       'filetypes': [ "python-magic" ], 
        'ftppoll' : ['dateparser' ],
        'mqtt': [ 'paho.mqtt>=1.5.1' ],
        'vip': [ 'netifaces' ],
        'redis': [ 'redis' ]
     }) 
+    extras_require['all'] = list(itertools.chain.from_iterable(extras_require.values()))
+
+